# RAG Memory

> Use this tool when you need to enhance AI assistants with knowledge graph-based information retrieval, combining semantic similarity and structural connections to retrieve contextual information. It solves problems related to document management, entity relationship creation, and hybrid search, providing outputs such as relevant documents and entities. Ideal for applications requiring persistent memory and complex knowledge representations, such as question answering and conversational AI systems.

Canonical page: https://skillsregistry.net/skills/rag-memory  
JSON: https://api.skillsregistry.net/v1/skills/rag-memory

## Description

RAG Memory MCP Server provides AI assistants with a knowledge graph-enhanced retrieval system that combines vector search with graph-based relationships. Developed by ttommyth, it offers tools for document management (storing, chunking, embedding), knowledge graph operations (creating entities and relationships), and hybrid search capabilities that leverage both semantic similarity and structural connections. The implementation uses SQLite with vector extensions for efficient storage and retrieval, making it particularly valuable for applications requiring persistent memory, contextual information retrieval, and the ability to build complex knowledge representations that evolve over time.

## Trust

- **Trust score (0–1):** 0.80
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/rag-memory)
- **Repository:** <https://github.com/ttommyth/rag-memory-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "rag-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rag-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rag-memory/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt